Commit Graph
21 Commits
Author SHA1 Message Date
MythEclipse 25c86dcc30 fix(ai-moderation): raise retry backoffs and cooldowns, make 429 retryable, reduce prompt false positives 2026-06-05 21:47:02 +07:00
MythEclipse 2f3d7e1d61 feat(ai-moderation): introduce user reputation and channel culture context
Implements a context-aware moderation system by tracking user behavior
and channel-specific norms to improve AI decision-making accuracy.

- Adds `user_reputations` table to track trust scores, clean streaks,
  and infraction history.
- Adds `channel_cultures` table to store AI-generated summaries of
  channel-specific norms and slang.
- Implements `userReputationStore` to autonomously update user scores
  based on moderation outcomes (clean vs. flagged).
- Implements `cultureLearner` and `channelCultureStore` to manage
  evolving channel contexts.
- Enhances LLM prompts to inject user reputation (trust scores,
  history) and channel culture summaries, enabling "wisdom-based"
  moderation (e.g., giving benefit of the doubt to high-trust users).
- Integrates reputation and culture updates into the existing
  `aiAnalyzer` pipeline.
2026-06-05 18:04:57 +07:00
MythEclipse 09f6e80ddd fix(ai-moderation): resolve race conditions and implement processing state
Introduces a `processing` state to the AI analysis lifecycle to prevent
duplicate processing of the same messages.

- Implements row-level locking using `FOR UPDATE SKIP LOCKED` in
  `messageStore.ts` to ensure atomic message acquisition.
- Adds a `processing` status to the `AIStatus` type and database schema.
- Fixes a TOCTOU race condition in `aiAnalyzer.ts` by synchronizing
  the conversation processing lock before async database operations.
- Implements `revertStuckProcessingMessages` to recover messages stuck
  in the `processing` state due to worker crashes or timeouts.
- Updates `processBatch` and scheduling logic to correctly manage and
  release conversation-level locks.
2026-06-05 16:36:14 +07:00
MythEclipse d1d4510ce8 chore(format): auto-format files with biome 2026-06-04 18:52:56 +07:00
MythEclipse ce8a42f5fd feat(ai-moderation): eliminate LLM-based badword detection in favor of pure rule-based matching 2026-06-04 17:33:08 +07:00
MythEclipse 5d9713b162 chore(config): update TELE_UPLOAD_URL domain across all services 2026-06-04 17:12:02 +07:00
MythEclipse d81aaf2b4a feat(db): add migration to drop unused AI columns and dynamically resolve initial migration tag 2026-06-02 23:55:12 +07:00
MythEclipse f10fa9aa88 feat(discord-gateway): export correctedModerationsTable from database schema 2026-06-02 23:05:37 +07:00
MythEclipse eb16c1f504 ``` 2026-06-02 23:05:33 +07:00
MythEclipse 0cd4f197e9 No staged changes found — the staging area is empty. Stage some files first with git add, then I can help craft the commit message. 2026-06-02 23:05:06 +07:00
MythEclipse f163ead3cf feat(discord-gateway): add local badword pre-filter, accurate token estimation, Piscina maxThreads config, and PromptMode support 2026-06-02 22:50:23 +07:00
MythEclipse 1e1fbb4583 fix(discord-gateway): require LLM API key only when AI analysis is enabled 2026-06-02 21:46:15 +07:00
MythEclipse 19028cf244 refactor: migrate discord-gateway from winston to @bete/shared/logger and utils
- Replace all local logger imports (../../shared/logger/logger.js) with @bete/shared/logger across 26 files
- Remove winston dependency, add pino to discord-gateway package.json
- Delete shared/logger/logger.ts (winston-based, 132 lines) and serialization.ts (109 lines)
- Replace local retryWithBackoff imports with @bete/shared/utils across 6 files
- Delete shared/utils/retry.ts (42 lines)
- Add CustomLogger type alias to @bete/shared/logger for backwards compatibility
- Remove logger param from all retryWithBackoff calls and uploadToTele interfaces
- Frontend: convert entity type files to re-exports from shared/api/client.ts
- Full monorepo typecheck clean (4/4 packages)

35 files changed, 42 insertions(+), 488 deletions(-)
2026-06-02 21:23:12 +07:00
MythEclipse b23ccf0837 chore: session auto-commit 2026-06-02 17:12:42 +07:00
MythEclipse 498ab73d62 chore: auto-commit task - 2026-06-02 17:08:42 +07:00
MythEclipse 406a6cbf79 refactor: migrate sticker cache to PostgreSQL, remove versioning
- Replace file-based sticker cache (.dat + index.json) with PostgreSQL sticker_cache table
- Remove model_version column and all versioning logic (git branch detection, GitHub API, CACHE_MODEL_VERSION)
- Strip VISION_MODEL_VERSION, logCacheEvent calls, and version filtering from SQL queries
- Remove STICKER_CACHE_DIR and STICKER_CACHE_MAX_SIZE_MB config variables
- Delete dead migration add_model_version_to_cache.sql

textCacheStore.ts reduced 482→204 lines (-57%)
stickerCache.ts reduced 210→144 lines (-31%)
Total: 11 files changed, 233 insertions, 591 deletions
2026-06-02 14:05:51 +07:00
MythEclipseandClaude Opus 4.8 e584a7941e fix(text-cache): apply model version migration on existing dbs
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 13:05:05 +07:00
MythEclipse 385fc0bbbf feat: add response logger for moderation/vision audit trail + cache model versioning
- Add responseLogger.ts with comprehensive logging: vision analysis, moderation
  analysis batches, cache hit/miss events, errors, retries, false positives,
  model version changes, cache invalidation
- Integrate responseLogger calls into llmModerationClient.ts (cache events,
  moderation results, errors, retries)
- Add model_version column to text_analysis_cache schema with composite
  index for efficient filtering
- Add migration SQL for model_version column
- Document CACHE_MODEL_VERSION in .env.example
2026-06-02 12:23:52 +07:00
MythEclipseandClaude Opus 4.8 64643bb066 perf: hapus semua cooldown/backoff delay — retry tanpa bottleneck
Semua retry sekarang instant (retries=0, minTimeout=0, maxTimeout=0):
- retry.ts (kedua) — default minTimeout/maxTimeout 0, factor 1
- config.ts (kedua) — DECODER_COOLDOWN_MS=0, AI_ANALYSIS_ERROR_COOLDOWN_MS=0
- llmModerationClient.ts (kedua) — retries 0 tanpa delay
- aiAnalyzer.ts (kedua) — retries 0, AI_ANALYSIS_ERROR_COOLDOWN jadi 0
- indonesianTextNormalizer.ts (kedua) — semua rate limit cooldown 0
- recorder.ts (kedua), teleUpload (3 files), uploader (2 files) — retry instant
- attachmentUploader (kedua) — retries 0
- syncRoutes.ts — BACKLOG_SYNC_COOLDOWN 0

20 files changed. Semua cooldown bottleneck dihapus.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 11:29:52 +07:00
MythEclipseandClaude Opus 4.6 58afa98132 fix(discord-gateway): skip migration if schema tables already exist
Instead of failing on CREATE TABLE when tables already exist, check
information_schema for all 10 schema tables. If all exist, skip
migration gracefully. This handles deployments where DB was created
by a previous deployment with different migration files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-01 23:09:04 +07:00
MythEclipseandClaude Opus 4.8 c48a0c5e3b refactor: split monolith into 3 microservices (frontend, backend, discord-gateway)
- Extract services into services/{frontend,backend,discord-gateway}
- Create packages/shared/ for shared logger, errors, utils, types
- Setup Modular MVC pattern in backend (controller→service→repository)
- Setup event-driven architecture in discord-gateway with Redis pub/sub
- Move Docker files to infra/docker/ with per-service Dockerfiles
- Update docker-compose.yml to use Traefik-only routing (no port exposes)
- Update GitHub Actions deploy workflow for multi-service matrix build
- Fix all import paths and resolve type errors across all services
- All 3 services pass tsc --noEmit clean

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-01 21:44:29 +07:00